[PATCH 04/21] Generic percpu refcounting

From: Kent Overstreet
Date: Mon May 13 2013 - 21:25:18 EST


This implements a refcount with similar semantics to
atomic_get()/atomic_dec_and_test() - but percpu.

It also implements two stage shutdown, as we need it to tear down the
percpu counts. Before dropping the initial refcount, you must call
percpu_ref_kill(); this puts the refcount in "shutting down mode" and
switches back to a single atomic refcount with the appropriate barriers
(synchronize_rcu()).

It's also legal to call percpu_ref_kill() multiple times - it only returns
true once, so callers don't have to reimplement shutdown synchronization.

[akpm@xxxxxxxxxxxxxxxxxxxx: fix build]
[akpm@xxxxxxxxxxxxxxxxxxxx: coding-style tweak]
Signed-off-by: Kent Overstreet <koverstreet@xxxxxxxxxx>
Cc: Zach Brown <zab@xxxxxxxxxx>
Cc: Felipe Balbi <balbi@xxxxxx>
Cc: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
Cc: Mark Fasheh <mfasheh@xxxxxxxx>
Cc: Joel Becker <jlbec@xxxxxxxxxxxx>
Cc: Rusty Russell <rusty@xxxxxxxxxxxxxxx>
Cc: Jens Axboe <axboe@xxxxxxxxx>
Cc: Asai Thambi S P <asamymuthupa@xxxxxxxxxx>
Cc: Selvan Mani <smani@xxxxxxxxxx>
Cc: Sam Bradshaw <sbradshaw@xxxxxxxxxx>
Cc: Jeff Moyer <jmoyer@xxxxxxxxxx>
Cc: Al Viro <viro@xxxxxxxxxxxxxxxxxx>
Cc: Benjamin LaHaise <bcrl@xxxxxxxxx>
Cc: Tejun Heo <tj@xxxxxxxxxx>
Cc: Oleg Nesterov <oleg@xxxxxxxxxx>
Cc: Christoph Lameter <cl@xxxxxxxxxxxxxxxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxxxxx>
Reviewed-by: "Theodore Ts'o" <tytso@xxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
include/linux/percpu-refcount.h | 118 +++++++++++++++++++++++++++++++++
lib/Makefile | 2 +-
lib/percpu-refcount.c | 140 ++++++++++++++++++++++++++++++++++++++++
3 files changed, 259 insertions(+), 1 deletion(-)
create mode 100644 include/linux/percpu-refcount.h
create mode 100644 lib/percpu-refcount.c

diff --git a/include/linux/percpu-refcount.h b/include/linux/percpu-refcount.h
new file mode 100644
index 0000000..5bd35c7
--- /dev/null
+++ b/include/linux/percpu-refcount.h
@@ -0,0 +1,118 @@
+/*
+ * Dynamic percpu refcounts:
+ * (C) 2012 Google, Inc.
+ * Author: Kent Overstreet <koverstreet@xxxxxxxxxx>
+ *
+ * This implements a refcount with similar semantics to atomic_t - atomic_inc(),
+ * atomic_dec_and_test() - but percpu.
+ *
+ * There's one important difference between percpu refs and normal atomic_t
+ * refcounts; you have to keep track of your initial refcount, and then when you
+ * start shutting down you call percpu_ref_kill() _before_ dropping the initial
+ * refcount.
+ *
+ * Before you call percpu_ref_kill(), percpu_ref_put() does not check for the
+ * refcount hitting 0 - it can't, if it was in percpu mode. percpu_ref_kill()
+ * puts the ref back in single atomic_t mode, collecting the per cpu refs and
+ * issuing the appropriate barriers, and then marks the ref as shutting down so
+ * that percpu_ref_put() will check for the ref hitting 0. After it returns,
+ * it's safe to drop the initial ref.
+ *
+ * USAGE:
+ *
+ * See fs/aio.c for some example usage; it's used there for struct kioctx, which
+ * is created when userspaces calls io_setup(), and destroyed when userspace
+ * calls io_destroy() or the process exits.
+ *
+ * In the aio code, kill_ioctx() is called when we wish to destroy a kioctx; it
+ * calls percpu_ref_kill(), then hlist_del_rcu() and sychronize_rcu() to remove
+ * the kioctx from the proccess's list of kioctxs - after that, there can't be
+ * any new users of the kioctx (from lookup_ioctx()) and it's then safe to drop
+ * the initial ref with percpu_ref_put().
+ *
+ * Code that does a two stage shutdown like this often needs some kind of
+ * explicit synchronization to ensure the initial refcount can only be dropped
+ * once - percpu_ref_kill() does this for you, it returns true once and false if
+ * someone else already called it. The aio code uses it this way, but it's not
+ * necessary if the code has some other mechanism to synchronize teardown.
+ * around.
+ */
+
+#ifndef _LINUX_PERCPU_REFCOUNT_H
+#define _LINUX_PERCPU_REFCOUNT_H
+
+#include <linux/atomic.h>
+#include <linux/kernel.h>
+#include <linux/percpu.h>
+#include <linux/rcupdate.h>
+
+struct percpu_ref {
+ atomic_t count;
+ unsigned __percpu *pcpu_count;
+};
+
+int percpu_ref_init(struct percpu_ref *ref);
+int percpu_ref_tryget(struct percpu_ref *ref);
+int percpu_ref_put_initial_ref(struct percpu_ref *ref);
+
+/**
+ * percpu_ref_get - increment a dynamic percpu refcount
+ *
+ * Analagous to atomic_inc().
+ */
+static inline void percpu_ref_get(struct percpu_ref *ref)
+{
+ unsigned __percpu *pcpu_count;
+
+ preempt_disable();
+
+ pcpu_count = ACCESS_ONCE(ref->pcpu_count);
+
+ if (pcpu_count)
+ __this_cpu_inc(*pcpu_count);
+ else
+ atomic_inc(&ref->count);
+
+ preempt_enable();
+}
+
+/**
+ * percpu_ref_put - decrement a dynamic percpu refcount
+ *
+ * Returns true if the result is 0, otherwise false; only checks for the ref
+ * hitting 0 after percpu_ref_kill() has been called. Analagous to
+ * atomic_dec_and_test().
+ */
+static inline int percpu_ref_put(struct percpu_ref *ref)
+{
+ unsigned __percpu *pcpu_count;
+ int ret = 0;
+
+ preempt_disable();
+
+ pcpu_count = ACCESS_ONCE(ref->pcpu_count);
+
+ if (pcpu_count)
+ __this_cpu_dec(*pcpu_count);
+ else
+ ret = atomic_dec_and_test(&ref->count);
+
+ preempt_enable();
+
+ return ret;
+}
+
+unsigned percpu_ref_count(struct percpu_ref *ref);
+int percpu_ref_kill(struct percpu_ref *ref);
+
+/**
+ * percpu_ref_dead - check if a dynamic percpu refcount is shutting down
+ *
+ * Returns true if percpu_ref_kill() has been called on @ref, false otherwise.
+ */
+static inline int percpu_ref_dead(struct percpu_ref *ref)
+{
+ return ref->pcpu_count == NULL;
+}
+
+#endif
diff --git a/lib/Makefile b/lib/Makefile
index e9c52e1..25a0ce1 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -13,7 +13,7 @@ lib-y := ctype.o string.o vsprintf.o cmdline.o \
sha1.o md5.o irq_regs.o reciprocal_div.o argv_split.o \
proportions.o flex_proportions.o prio_heap.o ratelimit.o show_mem.o \
is_single_threaded.o plist.o decompress.o kobject_uevent.o \
- earlycpio.o
+ earlycpio.o percpu-refcount.o

obj-$(CONFIG_ARCH_HAS_DEBUG_STRICT_USER_COPY_CHECKS) += usercopy.o
lib-$(CONFIG_MMU) += ioremap.o
diff --git a/lib/percpu-refcount.c b/lib/percpu-refcount.c
new file mode 100644
index 0000000..4a0155b
--- /dev/null
+++ b/lib/percpu-refcount.c
@@ -0,0 +1,140 @@
+#define pr_fmt(fmt) "%s: " fmt "\n", __func__
+
+#include <linux/kernel.h>
+#include <linux/percpu-refcount.h>
+
+/*
+ * The trick to implementing percpu refcounts is shutdown. We can't detect the
+ * ref hitting 0 on every put - this would require global synchronization and
+ * defeat the whole purpose of using percpu refs.
+ *
+ * What we do is require the user to keep track of the initial refcount; we know
+ * the ref can't hit 0 before the user drops the initial ref, so as long as we
+ * convert to non percpu mode before the initial ref is dropped everything
+ * works.
+ *
+ * Converting to non percpu mode is done with some RCUish stuff in
+ * percpu_ref_kill. Additionally, we need a bias value so that the atomic_t
+ * can't hit 0 before we've added up all the percpu refs.
+ */
+
+#define PCPU_COUNT_BIAS (1ULL << 31)
+
+int percpu_ref_tryget(struct percpu_ref *ref)
+{
+ int ret = 1;
+
+ preempt_disable();
+
+ if (!percpu_ref_dead(ref))
+ percpu_ref_get(ref);
+ else
+ ret = 0;
+
+ preempt_enable();
+
+ return ret;
+}
+
+unsigned percpu_ref_count(struct percpu_ref *ref)
+{
+ unsigned __percpu *pcpu_count;
+ unsigned count = 0;
+ int cpu;
+
+ preempt_disable();
+
+ count = atomic_read(&ref->count);
+
+ pcpu_count = ACCESS_ONCE(ref->pcpu_count);
+
+ if (pcpu_count)
+ for_each_possible_cpu(cpu)
+ count += *per_cpu_ptr(pcpu_count, cpu);
+
+ preempt_enable();
+
+ return count;
+}
+
+/**
+ * percpu_ref_init - initialize a dynamic percpu refcount
+ *
+ * Initializes the refcount in single atomic counter mode with a refcount of 1;
+ * analagous to atomic_set(ref, 1).
+ */
+int percpu_ref_init(struct percpu_ref *ref)
+{
+ atomic_set(&ref->count, 1 + PCPU_COUNT_BIAS);
+
+ ref->pcpu_count = alloc_percpu(unsigned);
+ if (!ref->pcpu_count)
+ return -ENOMEM;
+
+ return 0;
+}
+
+/**
+ * percpu_ref_kill - prepare a dynamic percpu refcount for teardown
+ *
+ * Must be called before dropping the initial ref, so that percpu_ref_put()
+ * knows to check for the refcount hitting 0. If the refcount was in percpu
+ * mode, converts it back to single atomic counter mode.
+ *
+ * The caller must issue a synchronize_rcu()/call_rcu() before calling
+ * percpu_ref_put() to drop the initial ref.
+ *
+ * Returns true the first time called on @ref and false if @ref is already
+ * shutting down, so it may be used by the caller for synchronizing other parts
+ * of a two stage shutdown.
+ */
+int percpu_ref_kill(struct percpu_ref *ref)
+{
+ unsigned __percpu *pcpu_count;
+ unsigned __percpu *old;
+ unsigned count = 0;
+ int cpu;
+
+ pcpu_count = ACCESS_ONCE(ref->pcpu_count);
+
+ do {
+ if (!pcpu_count)
+ return 0;
+
+ old = pcpu_count;
+ pcpu_count = cmpxchg(&ref->pcpu_count, old, NULL);
+ } while (pcpu_count != old);
+
+ synchronize_sched();
+
+ for_each_possible_cpu(cpu)
+ count += *per_cpu_ptr(pcpu_count, cpu);
+
+ free_percpu(pcpu_count);
+
+ pr_debug("global %lli pcpu %i",
+ (int64_t) atomic_read(&ref->count), (int) count);
+
+ atomic_add((int) count - PCPU_COUNT_BIAS, &ref->count);
+
+ return 1;
+}
+
+/**
+ * percpu_ref_put_initial_ref - safely drop the initial ref
+ *
+ * A percpu refcount needs a shutdown sequence before dropping the initial ref,
+ * to put it back into single atomic_t mode with the appropriate barriers so
+ * that percpu_ref_put() can safely check for it hitting 0 - this does so.
+ *
+ * Returns true if @ref hit 0.
+ */
+int percpu_ref_put_initial_ref(struct percpu_ref *ref)
+{
+ if (percpu_ref_kill(ref)) {
+ return percpu_ref_put(ref);
+ } else {
+ WARN_ON(1);
+ return 0;
+ }
+}
--
1.8.2.1

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/